Hyung Joon Joo
Korea University · Medicine
About the Lab
Professor Hyung Joon Joo's research lab specializes in biomedical data science and regenerative medicine, with a strong focus on leveraging artificial intelligence and natural language processing (NLP) to advance clinical decision-making and medical data analysis. The lab develops deep learning-based language models tailored for Korean medical texts, enabling precise extraction of clinical information from pathology reports and electronic health records. Additionally, the lab investigates cellular mechanisms underlying endothelial and mesenchymal stem cell differentiation, aiming to optimize regenerative therapies for cardiovascular diseases. Their interdisciplinary work bridges clinical cardiology, stem cell biology, and AI-driven healthcare solutions.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15This study was the sub-analysis of the prospective multi-center registry of DIAMOND (Diabetic acute myocardial infarction Disease) in Korea. This is the observational study supported by Bayer HealthCare, Korea. Study number is 15614. First patient first visit was 02 April 2010 and last patient last visit was 09 December 2013.
With advances in deep learning and natural language processing (NLP), the analysis of medical texts is becoming increasingly important. Nonetheless, despite the importance of processing medical texts, no research on Korean medical-specific language models has been conducted. The Korean medical text is highly difficult to analyze because of the agglutinative characteristics of the language, as well as the complex terminologies in the medical domain. To solve this problem, we collected a Korean me
Successful differentiation and expansion of endothelial cells (ECs) from embryonic stem cell (ESC)-derived Flk1(+) mesodermal precursor cells (MPCs) requires supplementation of vascular endothelial growth factor-A (VEGF-A). While analyzing VEGF-A/VEGFR2 downstream signaling pathway that underlies the VEGF-A-induced differentiation and expansion of ECs, we fortuitously found that Rho-associated protein kinase (ROCK) inhibitor Y27632 profoundly promoted the differentiation and expansion of ECs fro
Pathology reports contain the essential data for both clinical and research purposes. However, the extraction of meaningful, qualitative data from the original document is difficult due to the narrative and complex nature of such reports. Keyword extraction for pathology reports is necessary to summarize the informative text and reduce intensive time consumption. In this study, we employed a deep learning model for the natural language process to extract keywords from pathology reports and prese
BACKGROUND: Owing to the prevalence of the coronavirus disease (COVID-19), coping with clinical issues at the individual level has become important to the healthcare system. Accordingly, precise initiation of treatment after a hospital visit is required for expedited processes and effective diagnoses of outpatients. To achieve this, artificial intelligence in medical natural language processing (NLP), such as a healthcare chatbot or a clinical decision support system, can be suitable tools for a
studies showed the multipotent differentiation potentials of ADSC, even differentiation into cardiomyocytes. Many pre-clinical animal studies have also demonstrated promising therapeutic results of ADSC. Furthermore, there were several clinical trials showing the positive results in acute myocardial infarction using ADSC. The present article covers the brief introduction, the suggested therapeutic mechanisms, application methods including cell dose and delivery, and human clinical trials of ADSC
Angiopoietin-1 (Ang1) plays a crucial role in vascular and hematopoietic development, mainly through its cognate receptor Tie2. However, little is known about the precise role of Ang1 in embryonic stem cell (ESC) differentiation. In the present study, we used COMP-Ang1 (a soluble and potent variant of Ang1) to explore the effect of Ang1 on endothelial and hematopoietic differentiation of mouse ESCs in an OP9 coculture system and found that Ang1 promoted endothelial cell (EC) differentiation from
Background: Accurate medical advice is paramount in ensuring optimal patient care, and misinformation can lead to misguided decisions with potentially detrimental health outcomes. The emergence of large language models (LLMs) such as OpenAI's GPT-4 has spurred interest in their potential health care applications, particularly in automated medical consultation. Yet, rigorous investigations comparing their performance to human experts remain sparse. Objective: This study aims to compare the medica
OBJECTIVES: We sought to investigate the long-term clinical outcomes of patients with coronary artery aneurysm (CAA) after drug-eluting stent (DES) implantation, compared with patients without CAA. BACKGROUND: CAA developed after DES implantation is a rare but associated with poor clinical outcome. METHODS: We retrospectively compared 78 patients with CAA after DES implantation with 269 patients without CAA who underwent DES implantation for complex lesions (controls). The primary endpoint was d
Clopidogrel is the mainstay for antiplatelet treatment after percutaneous coronary intervention (PCI). The relationship of platelet reactivity and genetic polymorphism with clinical outcomes with newer-generation drug-eluting stents is unclear. We analysed 4,587 patients for the most powerful single-nucleotide polymorphisms (CYP2C19, CYP2C9, ABCB1, PON1, and P2Y12) related to on-treatment platelet reactivity (OPR). The optimal cut-off value of high OPR for major adverse thrombotic events was 266
baPWV was associated with the composite coronary and carotid atherosclerotic burden in a community-based asymptomatic population.
<i>Ex vivo</i> treatment of EGCG inhibited platelet adhesion and aggregation without changes in P-selectin and PAC-1 expression. There was no additional suppressions in platelet aggregation stimulated by AA in the ASA group and ADP in the CPD and TCG groups.
A novel tissue engineering strategy using 3D bio-print technology has become a promising therapeutic method for acute myocardial infarction (AMI) in an animal model. However, the application of 3D bio-printed tissue remains limited due to poor graft survival. Therefore, it is a scientific priority to enhance graft survival by precisely adjusting the 3D environment of encapsulated cells. In this study, novel transplantable 3D cardiac mesh (cMesh) tissue with a porous mesh structure was presented
BACKGROUND: Metabolic abnormalities such as dyslipidemia, glucose and high blood pressure are common in diabetic patients. Visit-to-visit variabilities in these measures have been reported as potential residual cardiovascular risk factors. However, the relationship between these variabilities and their effects on cardiovascular prognosis have not been studied. METHODS: A total of 22,310 diabetic patients with ≥ 3 measurements of systolic blood pressure (SBP), blood glucose, total cholesterol (TC
Research Areas
Dive deeper into Hyung Joon Joo's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.